A Deep Active Contour Model for Delineating Glacier Calving Fronts
International audience This work has been accepted by IEEE TGRS for publication in a future issue. Choosing how to encode a realworld problem as a machine learning task is an important design decision in machine learning. The task of glacier calving front modeling has often been approached as a sema...
Published in: | IEEE Transactions on Geoscience and Remote Sensing |
---|---|
Main Authors: | , , , , , |
Other Authors: | , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2023
|
Subjects: | |
Online Access: | https://hal.science/hal-04430672 https://hal.science/hal-04430672/document https://hal.science/hal-04430672/file/2307.03461.pdf https://doi.org/10.1109/TGRS.2023.3296539 |
id |
ftunivrennes1hal:oai:HAL:hal-04430672v1 |
---|---|
record_format |
openpolar |
spelling |
ftunivrennes1hal:oai:HAL:hal-04430672v1 2024-05-19T07:40:43+00:00 A Deep Active Contour Model for Delineating Glacier Calving Fronts Heidler, Konrad Mou, Lichao Loebel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang Technische Universität Munchen - Technical University Munich - Université Technique de Munich (TUM) Technische Universität Dresden = Dresden University of Technology (TU Dresden) Observation de l’environnement par imagerie complexe (OBELIX) SIGNAL, IMAGE ET LANGAGE (IRISA-D6) Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) 2023 https://hal.science/hal-04430672 https://hal.science/hal-04430672/document https://hal.science/hal-04430672/file/2307.03461.pdf https://doi.org/10.1109/TGRS.2023.3296539 en eng HAL CCSD Institute of Electrical and Electronics Engineers info:eu-repo/semantics/altIdentifier/arxiv/2307.03461 info:eu-repo/semantics/altIdentifier/doi/10.1109/TGRS.2023.3296539 hal-04430672 https://hal.science/hal-04430672 https://hal.science/hal-04430672/document https://hal.science/hal-04430672/file/2307.03461.pdf ARXIV: 2307.03461 doi:10.1109/TGRS.2023.3296539 info:eu-repo/semantics/OpenAccess ISSN: 0196-2892 IEEE Transactions on Geoscience and Remote Sensing https://hal.science/hal-04430672 IEEE Transactions on Geoscience and Remote Sensing, 2023, 61, pp.5615912. ⟨10.1109/TGRS.2023.3296539⟩ Active contours edge detection Greenland glacier front uncertainty [SDE.IE]Environmental Sciences/Environmental Engineering [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] info:eu-repo/semantics/article Journal articles 2023 ftunivrennes1hal https://doi.org/10.1109/TGRS.2023.3296539 2024-04-24T23:58:09Z International audience This work has been accepted by IEEE TGRS for publication in a future issue. Choosing how to encode a realworld problem as a machine learning task is an important design decision in machine learning. The task of glacier calving front modeling has often been approached as a semantic segmentation task. Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called "Charting Outlines by Recurrent Adaptation" (COBRA), combines Convolutional Neural Networks (CNNs) for feature extraction and active contour models for the delineation. By training and evaluating on several large-scale datasets of Greenland's outlet glaciers, we show that this approach indeed outperforms the aforementioned methods based on segmentation and edgedetection. Finally, we demonstrate that explicit contour detection has benefits over pixel-wise methods when quantifying the models' prediction uncertainties. The project page containing the code and animated model predictions can be found at https://khdlr.github.io/COBRA/. Article in Journal/Newspaper glacier Greenland Université de Rennes 1: Publications scientifiques (HAL) IEEE Transactions on Geoscience and Remote Sensing 61 1 12 |
institution |
Open Polar |
collection |
Université de Rennes 1: Publications scientifiques (HAL) |
op_collection_id |
ftunivrennes1hal |
language |
English |
topic |
Active contours edge detection Greenland glacier front uncertainty [SDE.IE]Environmental Sciences/Environmental Engineering [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] |
spellingShingle |
Active contours edge detection Greenland glacier front uncertainty [SDE.IE]Environmental Sciences/Environmental Engineering [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Heidler, Konrad Mou, Lichao Loebel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang A Deep Active Contour Model for Delineating Glacier Calving Fronts |
topic_facet |
Active contours edge detection Greenland glacier front uncertainty [SDE.IE]Environmental Sciences/Environmental Engineering [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] |
description |
International audience This work has been accepted by IEEE TGRS for publication in a future issue. Choosing how to encode a realworld problem as a machine learning task is an important design decision in machine learning. The task of glacier calving front modeling has often been approached as a semantic segmentation task. Recent studies have shown that combining segmentation with edge detection can improve the accuracy of calving front detectors. Building on this observation, we completely rephrase the task as a contour tracing problem and propose a model for explicit contour detection that does not incorporate any dense predictions as intermediate steps. The proposed approach, called "Charting Outlines by Recurrent Adaptation" (COBRA), combines Convolutional Neural Networks (CNNs) for feature extraction and active contour models for the delineation. By training and evaluating on several large-scale datasets of Greenland's outlet glaciers, we show that this approach indeed outperforms the aforementioned methods based on segmentation and edgedetection. Finally, we demonstrate that explicit contour detection has benefits over pixel-wise methods when quantifying the models' prediction uncertainties. The project page containing the code and animated model predictions can be found at https://khdlr.github.io/COBRA/. |
author2 |
Technische Universität Munchen - Technical University Munich - Université Technique de Munich (TUM) Technische Universität Dresden = Dresden University of Technology (TU Dresden) Observation de l’environnement par imagerie complexe (OBELIX) SIGNAL, IMAGE ET LANGAGE (IRISA-D6) Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) |
format |
Article in Journal/Newspaper |
author |
Heidler, Konrad Mou, Lichao Loebel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang |
author_facet |
Heidler, Konrad Mou, Lichao Loebel, Erik Scheinert, Mirko Lefèvre, Sébastien Zhu, Xiao Xiang |
author_sort |
Heidler, Konrad |
title |
A Deep Active Contour Model for Delineating Glacier Calving Fronts |
title_short |
A Deep Active Contour Model for Delineating Glacier Calving Fronts |
title_full |
A Deep Active Contour Model for Delineating Glacier Calving Fronts |
title_fullStr |
A Deep Active Contour Model for Delineating Glacier Calving Fronts |
title_full_unstemmed |
A Deep Active Contour Model for Delineating Glacier Calving Fronts |
title_sort |
deep active contour model for delineating glacier calving fronts |
publisher |
HAL CCSD |
publishDate |
2023 |
url |
https://hal.science/hal-04430672 https://hal.science/hal-04430672/document https://hal.science/hal-04430672/file/2307.03461.pdf https://doi.org/10.1109/TGRS.2023.3296539 |
genre |
glacier Greenland |
genre_facet |
glacier Greenland |
op_source |
ISSN: 0196-2892 IEEE Transactions on Geoscience and Remote Sensing https://hal.science/hal-04430672 IEEE Transactions on Geoscience and Remote Sensing, 2023, 61, pp.5615912. ⟨10.1109/TGRS.2023.3296539⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/arxiv/2307.03461 info:eu-repo/semantics/altIdentifier/doi/10.1109/TGRS.2023.3296539 hal-04430672 https://hal.science/hal-04430672 https://hal.science/hal-04430672/document https://hal.science/hal-04430672/file/2307.03461.pdf ARXIV: 2307.03461 doi:10.1109/TGRS.2023.3296539 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1109/TGRS.2023.3296539 |
container_title |
IEEE Transactions on Geoscience and Remote Sensing |
container_volume |
61 |
container_start_page |
1 |
op_container_end_page |
12 |
_version_ |
1799480297294659584 |